LLM API Providers Leaderboard - Comparison of over 500 AI Model endpoints
Comparison of API provider performance across over 500 AI Model endpoints, including from OpenAI, Google, DeepSeek and others, across performance key metrics including price, output speed, latency, context window and more.
For more details including relating to our methodology, see our FAQs.
Further Analysis | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5 (max) | 1M | Proprietary | 61 | $2.34 | 52 | 59.37 | 68.98 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 61 | $2.34 | 54 | 92.02 | 101.34 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 61 | $2.34 | 54 | 68.75 | 78.07 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 60 | $1.80 | 52 | 33.85 | 43.47 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 60 | $1.80 | 53 | 31.96 | 41.48 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 60 | $1.80 | 52 | 37.79 | 47.35 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 60 | $3.15 | 66 | 89.02 | 96.58 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 60 | $3.33 | 72 | 77.06 | 84.05 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 60 | $10.17 | 67 | 100.32 | 107.75 | -- | ||
GPT-5.6 Sol (max) | 262k | Proprietary | 59 | $1.67 | 112 | 87.46 | 91.92 | -- | ||
GPT-5.6 Sol (max) | 1M | Proprietary | 59 | $1.86 | 63 | 133.04 | 140.92 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 59 | $1.23 | 53 | 15.97 | 25.41 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 59 | $1.23 | 53 | 15.32 | 24.69 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 59 | $1.23 | 53 | 18.31 | 27.69 | -- | ||
GPT-5.6 Sol (xhigh) | 1M | Proprietary | 58 | $1.17 | 60 | 48.54 | 56.89 | -- | ||
Kimi K3 (max) | 1.05M | Open | 57 | $0.86 | 35 | 3.94 | 75.56 | 57.30 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $0.91 | 164 | 1.13 | 16.39 | 12.21 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $1.27 | 106 | 1.59 | 25.25 | 18.93 | ||
Kimi K3 (max) | 1M | Open | 57 | $1.29 | 32 | 1.14 | 78.80 | 62.13 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $1.03 | 32 | 2.34 | 79.93 | 62.07 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $0.80 | 59 | 2.31 | 44.81 | 34.01 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $0.67 | 137 | 1.39 | 19.62 | 14.58 | ||
Kimi K3 (max) | 1.05M | Open | 57 | $3.18 | 83 | 1.68 | 31.66 | 23.98 | ||
Kimi K3 (max) | 205k | Open | 57 | $0.81 | 127 | 1.41 | 21.04 | 15.70 | ||
Kimi K3 (max) (FAST) | 1M | Open | 57 | $1.30 | 172 | 1.25 | 15.79 | 11.63 | ||
Claude Opus 5 (medium) | 1M | Proprietary | 56 | $0.72 | 53 | 6.59 | 16.04 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 56 | $0.72 | 51 | 7.77 | 17.57 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 56 | $0.72 | 53 | 3.69 | 13.19 | -- | ||
GPT-5.6 Sol (high) | 1M | Proprietary | 56 | $0.77 | 57 | 12.49 | 21.30 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 55 | $0.73 | 126 | 164.36 | 168.34 | -- | ||
GPT-5.6 Terra (max) | 262k | Proprietary | 55 | $0.98 | 155 | 163.86 | 167.08 | -- | ||
Grok 4.5 (high) | 500k | Proprietary | 54 | $0.44 | 56 | 8.01 | 16.87 | -- | ||
GPT-5.6 Sol (medium) | 1M | Proprietary | 54 | $0.51 | 55 | 4.57 | 13.62 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 53 | $2.22 | 81 | 160.81 | 167.00 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 53 | $1.64 | 73 | 230.69 | 237.55 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 53 | $1.72 | 74 | 188.06 | 194.80 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 53 | $1.96 | 78 | 201.38 | 207.79 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietary | 52 | $0.43 | 109 | 22.12 | 26.70 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietary | 51 | $0.07 | 172 | 121.89 | 124.80 | -- | ||
GPT-5.6 Luna (max) | 262k | Proprietary | 51 | $0.34 | 223 | 102.87 | 105.12 | -- | ||
GLM-5.2 (max) | 205k | Open | 51 | $0.36 | 169 | 5.77 | 20.57 | 11.84 | ||
GLM-5.2 (max) | 1M | Open | 51 | $0.42 | 239 | 1.52 | 12.00 | 8.38 | ||
GLM-5.2 (max) (NVFP4) | 1M | Open | 51 | $0.51 | 146 | 0.88 | 18.04 | 13.73 | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 51 | $0.42 | 41 | 2.42 | 63.29 | 48.70 | ||
GLM-5.2 (max) | 261k | Open | 51 | $0.58 | 121 | 1.54 | 22.26 | 16.58 | ||
GLM-5.2 (max) (NVFP4) | 1M | Open | 51 | -- | 221 | 1.24 | 12.56 | 9.06 | ||
GLM-5.2 (max) | 262k | Open | 51 | -- | 97 | 1.36 | 27.03 | 20.54 | ||
GLM-5.2 (max) (FP4) | 1.05M | Open | 51 | -- | 43 | 1.31 | 59.50 | 46.55 | ||
GLM-5.2 (max) (FP4) | 432k | Open | 51 | $1.06 | 305 | 1.13 | 9.33 | 6.56 | ||
GLM-5.2 (max) | 1.05M | Open | 51 | $0.44 | 438 | 1.85 | 7.55 | 4.56 | ||
GLM-5.2 (max) | 1M | Open | 51 | -- | 384 | 0.98 | 7.49 | 5.21 | ||
GLM-5.2 (max) | 262k | Open | 51 | $1.57 | 61 | 1.95 | 42.88 | 32.75 | ||
GLM-5.2 (max) | 1M | Open | 51 | -- | 74 | 1.23 | 35.12 | 27.11 | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 51 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 51 | $0.65 | 57 | 1.72 | 45.26 | 34.84 | ||
Muse Spark 1.1 (xhigh) | 1.05M | Proprietary | 51 | $0.29 | 105 | 2.70 | 26.53 | 19.07 | ||
Claude Opus 5 (low) | 1M | Proprietary | 51 | $0.43 | 51 | 3.02 | 12.89 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 51 | $0.43 | 51 | 3.83 | 13.60 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 51 | $0.43 | 55 | 2.82 | 11.86 | -- | ||
Gemini 3.5 Flash AI Studio | 1M | Proprietary | 50 | $0.69 | 171 | 24.33 | 27.25 | -- | ||
Gemini 3.6 Flash AI Studio | 1M | Proprietary | 50 | $0.56 | 220 | 15.11 | 17.39 | -- | ||
DeepSeek V4 Flash 0731 (max) | 1M | Open | 50 | $0.03 | -- | -- | -- | -- | ||
GPT-5.6 Sol (low) | 1M | Proprietary | 49 | $0.31 | 56 | 2.90 | 11.79 | -- | ||
GPT-5.6 Luna (xhigh) | 1M | Proprietary | 49 | $0.04 | 174 | 37.90 | 40.77 | -- | ||
GPT-5.6 Terra (high) | 1M | Proprietary | 49 | $0.30 | 105 | 2.01 | 6.78 | -- | ||
Kimi K3 (low) | 1.05M | Open | 47 | $0.24 | 33 | 4.77 | 80.13 | 60.29 | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietary | 46 | $0.34 | 122 | 24.79 | 28.88 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietary | 46 | $0.43 | 130 | 22.01 | 25.85 | -- | ||
GPT-5.6 Luna (high) | 1M | Proprietary | 46 | $0.03 | 162 | 8.87 | 11.95 | -- | ||
Qwen3.7 Max | 991k | Proprietary | 46 | $1.28 | 199 | 2.45 | 17.06 | 12.10 | ||
Qwen3.7 Max (FP8) | 262k | Proprietary | 46 | -- | -- | -- | -- | -- | ||
Qwen3.7 Max | 1M | Proprietary | 46 | $0.65 | 51 | 2.14 | 58.86 | 46.97 | ||
GPT-5.6 Terra (medium) | 1M | Proprietary | 46 | $0.16 | 101 | 1.75 | 6.71 | -- | ||
Gemini 3.5 Flash (medium) | 1M | Proprietary | 45* | -- | 158 | 17.32 | 20.47 | -- | ||
MiniMax-M3 (MXFP8) | 1M | Open | 44 | $0.18 | 66 | 1.35 | 39.50 | 30.51 | ||
MiniMax-M3 | 262k | Open | 44 | $0.11 | 286 | 1.16 | 9.91 | 7.00 | ||
MiniMax-M3 | 1M | Open | 44 | $0.20 | 71 | 0.88 | 36.22 | 28.27 | ||
MiniMax-M3 | 1M | Open | 44 | $0.13 | 84 | 1.64 | 31.28 | 23.71 | ||
MiniMax-M3 | 524k | Open | 44 | $0.13 | 31 | 1.27 | 81.20 | 63.95 | ||
MiniMax-M3 (FP8) | 1.05M | Open | 44 | $0.45 | 183 | 1.98 | 15.61 | 10.91 | ||
MiniMax-M3 (FP8) | 1M | Open | 44 | $0.12 | 89 | 1.45 | 29.66 | 22.56 | ||
MiniMax-M3 | 512k | Open | 44 | $0.14 | 70 | 1.32 | 36.94 | 28.50 | ||
MiniMax-M3 | 1.05M | Open | 44 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | Open | 44 | $0.31 | 55 | 1.17 | 90.04 | 79.75 | ||
DeepSeek V4 Pro (max) | 1M | Open | 44 | $0.90 | 91 | 1.47 | 54.93 | 47.98 | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 44 | $0.23 | 57 | 1.90 | 87.73 | 77.03 | ||
DeepSeek V4 Pro (max) | 1M | Open | 44 | $0.76 | 205 | 0.92 | 24.70 | 21.34 | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | Open | 44 | $0.43 | 49 | 1.78 | 101.51 | 89.50 | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 44 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 44 | $0.90 | 65 | 2.66 | 77.10 | 66.80 | ||
DeepSeek V4 Pro (max) | 1M | Open | 44 | $0.05 | 62 | 1.79 | 80.40 | 70.55 | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietary | 44* | -- | 114 | 75.33 | 79.73 | -- | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | Open | 43 | $0.30 | 58 | 1.19 | 43.98 | 34.21 | ||
DeepSeek V4 Pro (high) | 1.05M | Open | 43 | $0.94 | 71 | 2.72 | 37.74 | 27.99 | ||
DeepSeek V4 Pro (high) | 1M | Open | 43 | $0.94 | 87 | 1.61 | 30.38 | 22.99 | ||
DeepSeek V4 Pro (high) | 1M | Open | 43 | $0.04 | 58 | 1.67 | 44.63 | 34.34 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | Open | 43 | $0.42 | 51 | 1.80 | 50.90 | 39.24 | ||
DeepSeek V4 Pro (high) | 1M | Open | 43 | $0.78 | 174 | 0.94 | 15.29 | 11.48 | ||
DeepSeek V4 Pro (high) | 1.05M | Open | 43 | $0.20 | 55 | 1.71 | 46.67 | 35.94 | ||
DeepSeek V4 Pro (high) | 131k | Open | 43 | $0.68 | 120 | 0.97 | 21.79 | 16.64 | ||
MiMo-V2.5-Pro | 1.05M | Open | 42 | $0.05 | 50 | 1.83 | 51.84 | 40.01 | ||
MiMo-V2.5-Pro | 1.05M | Open | 42 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Open | 42 | $0.24 | 104 | 0.74 | 24.87 | 19.30 | ||
MiMo-V2.5-Pro | 1M | Open | 42 | $0.05 | 49 | 2.94 | 53.53 | 40.47 | ||
Kimi K2.7 Code (FP4) | 256k | Open | 42 | $0.64 | 231 | 1.84 | 13.66 | 9.66 | ||
Kimi K2.7 Code (FP8) | 65.5k | Open | 42 | $0.48 | 46 | 5.27 | 64.17 | 48.11 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.28 | 305 | 1.15 | 10.10 | 7.31 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.18 | 74 | 1.49 | 38.34 | 30.10 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.30 | 249 | 0.54 | 11.52 | 8.96 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.22 | 44 | 3.41 | 65.19 | 50.46 | ||
Kimi K2.7 Code (NVFP4) | 262k | Open | 42 | $0.21 | 445 | 0.63 | 6.77 | 5.01 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.20 | 105 | 0.94 | 26.87 | 21.18 | ||
Kimi K2.7 Code | 262k | Open | 42 | $0.18 | 60 | 0.81 | 46.30 | 37.16 | ||
Kimi K2.7 Code | 256k | Open | 42 | $0.22 | 50 | 2.82 | 57.59 | 44.73 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 42 | $0.42 | 64 | 1.45 | 9.25 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 42 | $0.62 | 65 | 1.97 | 9.63 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 524k | Proprietary | 42 | $0.48 | 67 | 2.03 | 9.45 | -- | ||
Hy3 (FP8) | 256k | Open | 41 | $0.03 | 74 | 2.87 | 36.68 | 27.05 | ||
Hy3 | 262k | Open | 41 | $0.04 | 69 | 2.78 | 39.26 | 29.19 | ||
Hy3 (FP8) | 262k | Open | 41 | $0.04 | 62 | 0.86 | 41.10 | 32.19 | ||
Hy3 | 262k | Open | 41 | $0.03 | 80 | 3.08 | 34.50 | 25.13 | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietary | 41 | $0.32 | 53 | 0.99 | 10.47 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 262k | Proprietary | 41 | $0.30 | 92 | 3.63 | 9.06 | -- | ||
Nex-N2-Pro (FP8) | 262k | Open | 41 | -- | 127 | 1.63 | 21.32 | 15.75 | ||
Inkling (FP8) | 131k | Open | 41 | $0.45 | 226 | 1.03 | 12.08 | 8.84 | ||
Inkling | 524k | Open | 41 | $0.61 | 100 | 0.63 | 25.67 | 20.03 | ||
Inkling | 262k | Open | 41 | -- | 86 | 1.87 | 31.04 | 23.34 | ||
GPT-5.6 Terra (low) | 1M | Proprietary | 40 | $0.13 | 99 | 1.64 | 6.68 | -- | ||
Inkling Small | 256k | Open | 40 | $0.07 | 95 | 1.67 | 27.96 | 21.04 | ||
Qwen3.6 Plus | 1M | Proprietary | 40 | $0.36 | 55 | 2.31 | 111.71 | 100.36 | ||
Qwen3.7 Plus | 1M | Proprietary | 39 | $0.23 | 53 | 2.61 | 49.45 | 37.47 | ||
Agnes 2.5 Pro Alpha | 1M | Proprietary | 39 | -- | 126 | 2.42 | 22.18 | 15.82 | ||
GPT-5.6 Luna (medium) | 1M | Proprietary | 38 | $0.02 | 163 | 2.27 | 5.34 | -- | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.16 | 221 | 1.13 | 13.72 | 10.32 | ||
Nemotron 3 Ultra | 262k | Open | 38 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 512k | Open | 38 | $0.40 | 156 | 0.72 | 18.47 | 14.55 | ||
Nemotron 3 Ultra | 262k | Open | 38 | -- | 90 | 4.46 | 35.26 | 25.25 | ||
Nemotron 3 Ultra BF16 | 262k | Open | 38 | -- | 96 | 5.32 | 34.38 | 23.82 | ||
Nemotron 3 Ultra | 256k | Open | 38 | $0.59 | 326 | 2.29 | 10.80 | 6.98 | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.24 | 78 | 1.26 | 36.80 | 29.14 | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.22 | 444 | 1.18 | 7.44 | 5.13 | ||
MiMo-V2.5 | 1.05M | Open | 37 | $0.01 | 100 | 2.05 | 27.03 | 19.99 | ||
MiMo-V2.5 | 1M | Open | 37 | $0.04 | 68 | 1.41 | 38.33 | 29.54 | ||
MiMo-V2.5 | 262k | Open | 37 | -- | 29 | 1.35 | 87.88 | 69.23 | ||
MiMo-V2.5 | 1.05M | Open | 37 | $0.02 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | Open | 37 | $0.01 | 74 | 3.03 | 36.65 | 26.90 | ||
Qwen3.6 27B FP8 | 262k | Open | 37 | $0.19 | 44 | 1.46 | 142.42 | 129.55 | ||
Qwen3.6 27B | 131k | Open | 37 | $0.28 | 464 | 1.03 | 14.34 | 12.23 | ||
Qwen3.6 27B | 262k | Open | 37 | $0.29 | 54 | 2.86 | 117.29 | 105.17 | ||
Qwen3.6 27B | 262k | Open | 37 | $0.29 | 55 | 3.84 | 115.27 | 102.41 | ||
Qwen3.6 27B (FP8) | 262k | Open | 37 | $0.19 | 42 | 3.43 | 150.17 | 134.86 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietary | 36 | $0.10 | 360 | 8.07 | 9.46 | -- | ||
Grok 4.3 (medium) | 524k | Proprietary | 36* | -- | 179 | 6.62 | 9.42 | -- | ||
Grok 4.3 (medium) | 200k | Proprietary | 36* | -- | 112 | 11.19 | 15.64 | -- | ||
Grok 4.3 (medium) | 1M | Proprietary | 36* | -- | 133 | 9.84 | 13.60 | -- | ||
Grok 4.3 (low) | 524k | Proprietary | 35* | -- | 167 | 3.47 | 6.47 | -- | ||
Grok 4.3 (low) | 200k | Proprietary | 35* | -- | 112 | 6.26 | 10.71 | -- | ||
Grok 4.3 (low) | 1M | Proprietary | 35* | -- | 135 | 4.69 | 8.40 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | Proprietary | 35* | -- | 153 | 1.00 | 4.27 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | -- | -- | -- | -- | ||
Kimi K2.6 (FP4) | 262k | Open | 35* | -- | 378 | 0.58 | 1.91 | -- | ||
Kimi K2.6 (FP8) | 262k | Open | 35* | -- | 38 | 1.81 | 14.81 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | 64 | 1.19 | 9.03 | -- | ||
Kimi K2.6 (INT4) | 262k | Open | 35* | -- | 89 | 1.37 | 6.97 | -- | ||
Kimi K2.6 (FP4) | 262k | Open | 35* | -- | 50 | 0.86 | 10.81 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | 217 | 1.18 | 3.48 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | 164 | 1.41 | 4.45 | -- | ||
Kimi K2.6 (NVFP4) | 262k | Open | 35* | -- | -- | -- | -- | -- | ||
Kimi K2.6 | 256k | Open | 35* | -- | 43 | 2.81 | 14.42 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | 196 | 1.97 | 4.52 | -- | ||
Kimi K2.6 | 262k | Open | 35* | -- | 43 | 2.10 | 13.69 | -- | ||
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | Proprietary | 34* | -- | 43 | 1.33 | 12.92 | -- | ||
GLM-5.2 (FP4) | 432k | Open | 34 | -- | 265 | 1.39 | 3.27 | -- | ||
GLM-5.2 | 262k | Open | 34 | -- | 43 | 1.86 | 13.50 | -- | ||
GLM-5.2 | 205k | Open | 34 | -- | 190 | 6.10 | 8.73 | -- | ||
GLM-5.2 (FP8) | 1.05M | Open | 34 | -- | 54 | 2.17 | 11.40 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietary | 34 | $0.15 | 106 | 0.79 | 5.51 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 262k | Proprietary | 34 | $0.20 | 128 | 0.74 | 4.64 | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 34 | -- | 104 | 1.57 | 6.39 | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 34 | -- | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 256k | Open | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.36 | 68 | 2.40 | 56.95 | 47.15 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.26 | 69 | 2.15 | 55.75 | 46.33 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.24 | 72 | 1.10 | 52.27 | 44.23 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.23 | 98 | 2.37 | 39.88 | 32.42 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.19 | 38 | 0.87 | 98.46 | 84.35 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.13 | 9 | 1.50 | 398.13 | 342.82 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 34 | $0.36 | 91 | 2.02 | 42.38 | 34.88 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.36 | 67 | 1.85 | 57.20 | 47.84 | ||
Hy3-preview | 262k | Open | 34* | -- | -- | -- | -- | -- | ||
Hy3-preview | 256k | Open | 34* | -- | 115 | 3.29 | 24.96 | 17.34 | ||
LongCat 2.0 (FP8) | 1M | Open | 33 | $0.12 | 43 | 2.69 | 61.31 | 46.89 | ||
GPT-5.6 Luna (low) | 1M | Proprietary | 33 | $0.01 | 155 | 2.00 | 5.22 | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 32 | $0.17 | 52 | 2.07 | 50.55 | 38.78 | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 32 | $0.12 | 60 | 10.31 | 52.16 | 33.48 | ||
Qwen3.5 122B A10B | 262k | Open | 32 | $0.26 | 136 | 2.37 | 20.70 | 14.66 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 32 | $0.26 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Open | 32 | $0.26 | 97 | 1.91 | 27.60 | 20.55 | ||
Qwen3.5 397B A17B | 262k | Open | 32* | -- | 64 | 2.16 | 9.94 | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 32* | -- | 37 | 0.92 | 14.34 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 32* | -- | 66 | 2.36 | 9.95 | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 32* | -- | 91 | 2.10 | 7.61 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 32* | -- | 12 | 130.53 | 172.21 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 32* | -- | 64 | 1.83 | 9.67 | -- | ||
Qwen3.6 35B A3B | 229k | Open | 32 | $0.19 | 143 | 2.25 | 43.59 | 37.83 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.17 | 75 | 2.15 | 81.24 | 72.38 | ||
Qwen3.6 35B A3B | 262k | Open | 32 | $0.23 | 106 | 1.09 | 56.75 | 50.93 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.09 | 44 | 0.63 | 133.94 | 122.00 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.47 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 32 | $0.19 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 32 | $0.21 | 90 | 1.51 | 66.68 | 59.64 | ||
Qwen3.6 35B A3B | 205k | Open | 32 | $0.19 | 142 | 1.40 | 42.88 | 37.96 | ||
DeepSeek V4 Pro | 1M | Open | 31* | -- | 94 | 1.74 | 7.06 | -- | ||
DeepSeek V4 Pro | 1M | Open | 31* | -- | 182 | 1.01 | 3.77 | -- | ||
DeepSeek V4 Pro | 1M | Open | 31* | -- | 62 | 1.62 | 9.73 | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietary | 31* | -- | 53 | 2.39 | 11.83 | -- | ||
Ring-2.6-1T | 262k | Open | 31 | $0.37 | 126 | 3.33 | 23.24 | 15.93 | ||
Qwen3.6 27B | 131k | Open | 30 | $0.39 | 459 | 1.03 | 2.12 | -- | ||
Qwen3.6 27B FP8 | 262k | Open | 30 | $0.23 | 37 | 1.20 | 14.64 | -- | ||
Qwen3.6 27B | 262k | Open | 30 | $0.40 | 58 | 3.78 | 12.47 | -- | ||
Qwen3.6 27B | 262k | Open | 30 | $0.40 | 58 | 77.87 | 86.52 | -- | ||
o3 | 200k | Proprietary | 30* | -- | 108 | 29.50 | 34.15 | -- | ||
o3 | 200k | Proprietary | 30* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietary | 30* | -- | 125 | 5.39 | 9.39 | -- | ||
Step 3.7 Flash | 256k | Open | 30 | $0.09 | 393 | 0.92 | 7.28 | 5.09 | ||
Step 3.7 Flash | 256k | Open | 30 | -- | 206 | 0.45 | 12.56 | 9.69 | ||
Mistral Medium 3.5 | 262k | Open | 30 | $0.61 | 49 | 2.20 | 52.79 | 40.47 | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.23 | 121 | 12.20 | 16.33 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 30 | $0.24 | 99 | 20.59 | 25.64 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.25 | 95 | 15.64 | 20.88 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.54 | 107 | 15.48 | 20.14 | -- | ||
Gemma 4 31B | 262k | Open | 29 | -- | 38 | 1.01 | 60.61 | 46.28 | ||
Gemma 4 31B (FP8) | 262k | Open | 29 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Open | 29 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | Open | 29 | $0.25 | 1,990 | 0.59 | 1.71 | 0.87 | ||
Gemma 4 31B (AI Studio) | 262k | Open | 29 | $0.00 | 35 | 1.09 | 64.55 | 49.27 | ||
Gemma 4 31B | 262k | Open | 29 | $0.03 | 57 | 2.67 | 41.95 | 30.49 | ||
Gemma 4 31B | 262k | Open | 29 | $0.01 | 11 | 4.14 | 206.62 | 157.20 | ||
Gemma 4 31B (FP8) | 262k | Open | 29 | $0.03 | 46 | 3.36 | 51.84 | 37.63 | ||
Gemma 4 31B | 131k | Open | 29 | $0.10 | 195 | 3.01 | 14.51 | 8.92 | ||
Gemma 4 31B | 256k | Open | 29 | $0.04 | 115 | 1.86 | 21.22 | 15.03 | ||
Gemma 4 31B | 131k | Open | 29 | $0.04 | 138 | 0.84 | 17.02 | 12.56 | ||
Gemma 4 31B (FP8) | 262k | Open | 29 | $0.10 | 68 | 1.28 | 34.19 | 25.55 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietary | 29 | $0.54 | -- | -- | -- | -- | ||
DeepSeek V4 Flash | 1M | Open | 29* | -- | 107 | 1.24 | 5.91 | -- | ||
DeepSeek V4 Flash | 1.05M | Open | 29* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash | 1M | Open | 29* | -- | 241 | 0.67 | 2.75 | -- | ||
DeepSeek V4 Flash | 1M | Open | 29* | -- | 41 | 3.07 | 15.33 | -- | ||
MiMo-V2.5-Pro | 1.05M | Open | 28* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Open | 28* | -- | 118 | 0.73 | 4.96 | -- | ||
MiMo-V2.5-Pro | 131k | Open | 28* | -- | 48 | 3.22 | 13.70 | -- | ||
MiMo-V2.5-Pro | 1.05M | Open | 28* | -- | 49 | 2.26 | 12.45 | -- | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 28 | $0.09 | 46 | 21.13 | 32.00 | -- | ||
Qwen3.5 122B A10B | 262k | Open | 28 | $0.19 | 149 | 2.37 | 5.74 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietary | 27 | $0.02 | 168 | 0.77 | 3.74 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 262k | Proprietary | 27 | $0.09 | 198 | 0.97 | 3.49 | -- | ||
Hy3-preview | 262k | Open | 26* | -- | -- | -- | -- | -- | ||
Hy3-preview | 328k | Open | 26* | -- | 100 | 2.47 | 7.49 | -- | ||
Ling-2.6-1T | 262k | Open | 26* | -- | -- | -- | -- | -- | ||
Gemini 2.5 Pro Vertex | 1M | Proprietary | 26 | $0.22 | 107 | 24.59 | 29.28 | -- | ||
Gemini 2.5 Pro (AI Studio) | 1M | Proprietary | 26 | $0.22 | 133 | 20.53 | 24.30 | -- | ||
Gemma 4 26B A4B | 1M | Open | 26 | $0.02 | 165 | 0.98 | 16.09 | 12.09 | ||
Gemma 4 26B A4B | 262k | Open | 26 | $0.04 | 23 | 3.61 | 110.93 | 85.86 | ||
Gemma 4 26B A4B AI Studio | 262k | Open | 26 | $0.00 | 47 | 1.04 | 54.12 | 42.46 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.03 | 75 | 1.18 | 34.30 | 26.49 | ||
Gemma 4 26B A4B | 262k | Open | 26 | $0.03 | 13 | 1.07 | 186.71 | 148.51 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.03 | 37 | 1.92 | 68.83 | 53.52 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.20 | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 26 | $0.04 | -- | -- | -- | -- | ||
NVIDIA Nemotron 3 Super | 262k | Open | 25 | $0.23 | 142 | 0.97 | 18.62 | 14.12 | ||
NVIDIA Nemotron 3 Super | 256k | Open | 25 | $0.34 | 323 | 1.83 | 9.57 | 6.20 | ||
NVIDIA Nemotron 3 Super | 262k | Open | 25 | $0.10 | 87 | 1.45 | 30.16 | 22.96 | ||
Gemini 3.1 Flash-Lite (AI Studio) | 1M | Proprietary | 25 | $0.04 | 288 | 5.84 | 7.58 | -- | ||
Grok 4.3 (Non-reasoning) | 524k | Proprietary | 25 | $0.99 | 171 | 0.73 | 3.66 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | Proprietary | 25 | $0.29 | 125 | 0.82 | 4.83 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 24 | $1.20 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 24 | $0.49 | 85 | 1.09 | 6.98 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 24 | $0.29 | 34 | 0.64 | 15.52 | -- | ||
Qwen3.6 35B A3B | 205k | Open | 24 | $0.42 | 175 | 1.62 | 4.47 | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 24 | $0.42 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 24 | $0.43 | 91 | 1.27 | 6.76 | -- | ||
Qwen3.6 35B A3B | 262k | Open | 24 | $0.63 | 169 | 2.23 | 5.19 | -- | ||
Qwen3.5 35B A3B FP8 | 262k | Open | 24 | $0.07 | 136 | 0.49 | 4.15 | -- | ||
Qwen3.5 35B A3B | 262k | Open | 24 | $0.24 | 173 | 2.08 | 4.97 | -- | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.06 | 478 | 0.74 | 5.96 | 4.18 | ||
gpt-oss-120b (high) | 116k | Open | 24 | $0.15 | 90 | 1.11 | 28.98 | 22.29 | ||
gpt-oss-120b (high) | 128k | Open | 24 | $0.09 | 159 | 1.14 | 16.87 | 12.59 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.02 | 43 | 0.70 | 59.29 | 46.88 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.02 | 34 | 1.47 | 75.04 | 58.85 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.08 | 309 | 1.77 | 9.85 | 6.46 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.03 | 93 | 0.90 | 27.78 | 21.50 | ||
gpt-oss-120b (high) (Turbo) | 131k | Open | 24 | $0.08 | 238 | 0.82 | 11.31 | 8.40 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.15 | 1,800 | 0.52 | 1.91 | 1.11 | ||
gpt-oss-120b (high) Vertex | 131k | Open | 24 | $0.05 | 402 | 0.39 | 6.60 | 4.97 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.05 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Open | 24 | $0.05 | 180 | 0.28 | 14.19 | 11.13 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.10 | 705 | 1.03 | 4.58 | 2.84 | ||
gpt-oss-120b (high) | 131k | Open | 24 | -- | 189 | 0.78 | 14.00 | 10.58 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.08 | 107 | 0.88 | 24.29 | 18.73 | ||
gpt-oss-120b (high) (Base) | 128k | Open | 24 | $0.08 | 238 | 1.02 | 11.53 | 8.40 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.12 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Open | 24 | $0.08 | 291 | 0.61 | 9.19 | 6.87 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.08 | 84 | 1.04 | 30.63 | 23.67 | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 87 | 1.21 | 6.93 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 103 | 1.02 | 5.89 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 88 | 1.00 | 6.71 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 24* | -- | 90 | 0.65 | 6.19 | -- | ||
Command A+ | 200k | Open | 23 | $0.00 | 196 | 0.38 | 13.14 | 10.21 | ||
Gemma 4 12B | 262k | Open | 22 | $0.08 | 44 | 2.64 | 59.65 | 45.61 | ||
Gemma 4 31B | 262k | Open | 22 | $0.03 | 65 | 1.99 | 9.71 | -- | ||
Gemma 4 31B | 131k | Open | 22 | $0.25 | 2,065 | 0.57 | 0.81 | -- | ||
Gemma 4 31B | 262k | Open | 22 | $0.04 | 115 | 1.33 | 5.69 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.10 | 55 | 1.24 | 10.30 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.03 | 54 | 2.94 | 12.20 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.03 | 8 | 3.73 | 70.38 | -- | ||
Gemma 4 31B | 131k | Open | 22 | $0.10 | 197 | 2.73 | 5.27 | -- | ||
Gemma 4 31B | 262k | Open | 22 | $0.04 | 6 | 3.15 | 84.82 | -- | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietary | 22 | $0.18 | 115 | 11.97 | 33.74 | 17.42 | ||
Qwen3.5 9B (FP8) | 262k | Open | 21 | $0.18 | 39 | 2.48 | 67.38 | 51.92 | ||
Qwen3.5 9B (FP8) | 262k | Open | 21 | $0.31 | 89 | 0.83 | 28.84 | 22.40 | ||
Mercury 2 | 128k | Proprietary | 21 | $0.08 | 809 | 3.62 | 4.24 | -- | ||
Qwen3 Coder Next | 128k | Open | 21 | $0.47 | 152 | 1.06 | 4.35 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.11 | 81 | 1.22 | 7.43 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.47 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.20 | 173 | 2.07 | 4.96 | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 21* | -- | -- | -- | -- | -- | ||
Apriel-v1.6-15B-Thinker | 131k | Open | 21* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 1M | Open | 20* | -- | 173 | 0.98 | 3.88 | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 27 | 1.83 | 20.26 | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 20* | -- | 79 | 2.22 | 8.54 | -- | ||
Gemma 4 26B A4B | 256k | Open | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 131 | 0.92 | 4.73 | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 20* | -- | 15 | 0.84 | 34.39 | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 24 | 2.32 | 23.35 | -- | ||
Qwen3.5 4B (FP8) | 262k | Open | 20* | -- | 29 | 0.68 | 88.29 | 70.09 | ||
North Mini Code | 256k | Open | 20 | $0.00 | 24 | 0.62 | 105.05 | 83.55 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietary | 20 | $0.23 | 119 | 10.59 | 31.66 | 16.85 | ||
Mistral Small 4 | 256k | Open | 20 | $0.10 | 159 | 0.79 | 16.51 | 12.57 | ||
Devstral 2 | 262k | Open | 19 | $0.00 | 49 | 1.38 | 11.64 | -- | ||
Nova 2.0 Lite (medium) | 1M | Proprietary | 19* | -- | 159 | 17.05 | 32.76 | 12.57 | ||
Qwen3.5 Omni Flash | 256k | Proprietary | 19* | -- | 239 | 2.03 | 4.13 | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 18 | $0.24 | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 18 | $0.24 | 148 | 19.97 | 36.82 | 13.48 | ||
Trinity Large Thinking | 262k | Open | 18 | $0.20 | 247 | 1.44 | 11.55 | 8.09 | ||
Trinity Large Thinking (FP8) | 262k | Open | 18 | $0.08 | 186 | 0.95 | 14.38 | 10.75 | ||
Magistral Medium 1.2 | 131k | Proprietary | 18 | $0.84 | 45 | 2.07 | 57.52 | 44.36 | ||
Nova 2.0 Lite (low) | 1M | Proprietary | 18* | -- | 144 | 9.54 | 26.89 | 13.89 | ||
HyperNova 60B 2605 | 131k | Open | 18 | $0.02 | 384 | 0.61 | 7.13 | 5.21 | ||
Devstral Small 2 | 256k | Open | 17 | $0.00 | 51 | 1.44 | 11.18 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.05 | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 17 | $0.04 | 155 | 0.73 | 16.82 | 12.87 | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.19 | 200 | 2.28 | 14.81 | 10.02 | ||
Qwen3 Next 80B A3B (FP8) | 262k | Open | 17 | $0.04 | 103 | 1.04 | 25.28 | 19.39 | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.03 | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | Proprietary | 17* | -- | -- | -- | -- | -- | ||
G9v3-3B | 131k | Open | 16 | $0.00 | -- | -- | -- | -- | ||
Qwen3.5 4B FP8 | 262k | Open | 16* | -- | 18 | 0.78 | 29.18 | -- | ||
Mistral Large 3 | 256k | Open | 16 | $0.08 | 188 | 1.19 | 3.86 | -- | ||
Mistral Large 3 | 256k | Open | 16 | $0.08 | 48 | 1.90 | 12.32 | -- | ||
Mistral Large 3 | 262k | Open | 16 | $0.08 | 53 | 1.09 | 10.50 | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning | 262k | Open | 15* | -- | -- | -- | -- | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) | 65.5k | Open | 15* | -- | 303 | 1.00 | 9.25 | 6.60 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Open | 15 | $0.02 | 251 | 1.02 | 10.99 | 7.98 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.03 | 727 | 1.07 | 4.51 | 2.75 | ||
gpt-oss-120b (low) Vertex | 131k | Open | 15 | $0.01 | 410 | 0.41 | 6.50 | 4.88 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 117 | 0.73 | 22.16 | 17.14 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.0042 | 28 | 1.47 | 90.25 | 71.02 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.05 | 1,738 | 0.56 | 2.00 | 1.15 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 330 | 1.84 | 9.42 | 6.06 | ||
gpt-oss-120b (low) | 128k | Open | 15 | $0.05 | 81 | 1.34 | 32.11 | 24.62 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Open | 15 | $0.01 | 183 | 0.26 | 13.93 | 10.94 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 91 | 1.02 | 28.63 | 22.09 | ||
gpt-oss-120b (low) | 131k | Open | 15 | -- | 157 | 0.77 | 16.71 | 12.75 | ||
gpt-oss-120b (low) | 128k | Open | 15 | $0.02 | 293 | 0.74 | 9.27 | 6.82 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 476 | 0.73 | 5.98 | 4.20 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | 101 | 0.91 | 25.78 | 19.90 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.01 | 169 | 0.90 | 15.68 | 11.82 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.03 | 145 | 33.76 | 51.06 | 13.84 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.01 | 101 | 0.47 | 25.12 | 19.72 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Open | 15 | $0.02 | 273 | 0.74 | 9.91 | 7.33 | ||
gpt-oss-20b (high) | 128k | Open | 15 | $0.08 | 167 | 0.79 | 15.76 | 11.98 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.02 | 94 | 1.06 | 27.76 | 21.36 | ||
gpt-oss-20b (high) Vertex | 131k | Open | 15 | $0.03 | 217 | 3.34 | 14.86 | 9.21 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.03 | 277 | 0.84 | 9.87 | 7.23 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.03 | 930 | 0.78 | 3.47 | 2.15 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.02 | -- | -- | -- | -- | ||
Nova 2.0 Pro Preview | 256k | Proprietary | 14 | $0.26 | 98 | 1.08 | 6.21 | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 931 | 0.81 | 3.49 | 2.15 | ||
gpt-oss-20b (low) | 128k | Open | 14* | -- | 274 | 0.73 | 9.85 | 7.30 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 143 | 0.90 | 18.41 | 14.01 | ||
gpt-oss-20b (low) | 128k | Open | 14* | -- | 168 | 0.84 | 15.71 | 11.90 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 87 | 11.79 | 40.56 | 23.01 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 103 | 1.12 | 25.45 | 19.46 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 302 | 0.90 | 9.18 | 6.63 | ||
gpt-oss-20b (low) Vertex | 131k | Open | 14* | -- | 128 | 1.46 | 21.02 | 15.64 | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.04 | 34 | 1.00 | 15.53 | -- | ||
Llama 4 Maverick (FP8) | 128k | Open | 14 | $0.03 | 116 | 1.12 | 5.44 | -- | ||
Llama 4 Maverick | 128k | Open | 14 | $0.03 | 230 | 0.85 | 3.03 | -- | ||
Llama 4 Maverick | 131k | Open | 14 | $0.06 | 124 | 1.09 | 5.13 | -- | ||
Llama 4 Maverick | 1.05M | Open | 14 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.03 | 35 | 0.67 | 15.13 | -- | ||
Llama 4 Maverick | 131k | Open | 14 | $0.06 | 81 | 0.82 | 7.02 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.02 | 120 | 0.85 | 5.03 | -- | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 14 | $0.03 | 320 | 1.02 | 8.84 | 6.25 | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Open | 14 | $0.02 | 265 | 1.04 | 10.46 | 7.53 | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 14 | $0.02 | 228 | 3.16 | 14.13 | 8.78 | ||
Solar Pro 3 | 131k | Proprietary | 14 | $0.11 | 22 | 2.49 | 114.59 | 89.68 | ||
Ling 2.6 Flash | 262k | Open | 14 | -- | 80 | 1.19 | 7.41 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 14* | -- | 178 | 0.84 | 3.65 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 183 | 2.26 | 5.00 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 104 | 0.63 | 5.42 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 140 | 0.93 | 4.49 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 14* | -- | 180 | 1.61 | 4.39 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 14* | -- | 183 | 2.15 | 4.89 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | Open | 13* | -- | 32 | 2.62 | 18.08 | -- | ||
Nova Premier | 1M | Proprietary | 13* | -- | 32 | 2.89 | 18.48 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Open | 12* | -- | 90 | 3.37 | 31.09 | 22.18 | ||
Mistral Small 4 | 262k | Open | 12* | -- | 147 | 0.86 | 4.26 | -- | ||
Gemma 4 E4B | 262k | Open | 12 | $0.01 | 89 | 0.79 | 28.74 | 22.36 | ||
Sarvam 105B (high) | 128k | Open | 12* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite | 1M | Proprietary | 12* | -- | 145 | 1.08 | 4.52 | -- | ||
Celeris-1 | 131k | Proprietary | 12 | -- | 2,038 | 0.65 | 0.90 | -- | ||
Magistral Small 1.2 | 128k | Open | 11 | $0.29 | 73 | 1.61 | 35.66 | 27.24 | ||
Magistral Small 1.2 | 131k | Open | 11 | $0.29 | 90 | 0.93 | 28.74 | 22.25 | ||
Ministral 3 14B | 262k | Open | 11 | $0.16 | 80 | 0.87 | 7.09 | -- | ||
Ministral 3 14B | 256k | Open | 11 | $0.16 | 176 | 1.16 | 4.00 | -- | ||
Nova 2.0 Omni | 1M | Proprietary | 11* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | Open | 10 | $0.01 | 48 | 0.59 | 11.06 | -- | ||
Llama 4 Scout | 128k | Open | 10 | $0.01 | -- | -- | -- | -- | ||
Llama 4 Scout Vertex | 1.31M | Open | 10 | $0.01 | 134 | 0.87 | 4.59 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.02 | 37 | 0.75 | 14.21 | -- | ||
Llama 4 Scout | 128k | Open | 10 | $0.01 | 163 | 0.86 | 3.93 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.01 | 51 | 0.98 | 10.87 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.01 | 446 | 0.74 | 1.86 | -- | ||
Hermes 4 70B (FP8) | 128k | Open | 10* | -- | 83 | 1.39 | 31.35 | 23.97 | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 10* | -- | 98 | 1.99 | 27.56 | 20.46 | ||
Llama 3.3 70B | 131k | Open | 9 | $0.14 | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Open | 9 | $0.11 | 117 | 0.68 | 4.96 | -- | ||
Llama 3.3 70B | 131k | Open | 9 | $0.09 | 301 | 0.98 | 2.64 | -- | ||
Llama 3.3 70B | 131k | Open | 9 | $0.02 | -- | -- | -- | -- | ||
Llama 3.3 70B (FP8) | 131k | Open | 9 | $0.02 | 63 | 2.65 | 10.60 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.09 | 283 | 1.84 | 3.60 | -- | ||
Llama 3.3 70B Base | 128k | Open | 9 | $0.02 | 13 | 3.51 | 41.86 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 75 | 0.89 | 7.55 | -- | ||
Llama 3.3 70B Turbo | 131k | Open | 9 | $0.16 | 91 | 1.57 | 7.06 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 93 | 2.40 | 7.74 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Open | 9 | $0.02 | 13 | 2.03 | 40.40 | -- | ||
Llama 3.3 70B | 24k | Open | 9 | $0.05 | 54 | 3.72 | 12.91 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 114 | 1.19 | 5.55 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.08 | 66 | 1.14 | 8.73 | -- | ||
Llama 3.3 70B | 100k | Open | 9 | $0.16 | 82 | 1.27 | 7.36 | -- | ||
Llama Nemotron Ultra Base | 131k | Open | 9* | -- | 51 | 2.39 | 51.31 | 39.13 | ||
ERNIE 4.5 300B A47B | 131k | Open | 9* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Open | 9* | -- | 39 | 2.37 | 67.24 | 51.89 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Open | 9* | -- | 82 | 4.00 | 34.53 | 24.42 | ||
Ministral 3 8B | 256k | Open | 9 | $0.18 | 242 | 1.09 | 3.16 | -- | ||
Ministral 3 8B | 262k | Open | 9 | $0.18 | 115 | 0.73 | 5.08 | -- | ||
Gemma 4 E4B | 262k | Open | 9* | -- | 89 | 0.75 | 6.34 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 9* | -- | 233 | 4.12 | 14.85 | 8.59 | ||
Hermes 4 405B (FP8) | 128k | Open | 9* | -- | 34 | 2.35 | 16.96 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Open | 9* | -- | 93 | 3.45 | 8.83 | -- | ||
Llama 3.1 405B | 128k | Open | 9* | -- | -- | -- | -- | -- | ||
LFM2.5-8B-A1B | 32.8k | Open | 8* | -- | 338 | 3.31 | 10.71 | 5.91 | ||
Ring-flash-2.0 | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Open | 8* | -- | -- | -- | -- | -- | ||
Command A | 288k | Open | 8* | -- | 57 | 1.78 | 10.54 | -- | ||
Command A | 256k | Open | 8* | -- | 41 | 3.26 | 15.39 | -- | ||
Llama 3.1 Nemotron 70B | 131k | Open | 8* | -- | 92 | 4.97 | 10.41 | -- | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Open | 7* | -- | 236 | 1.09 | 3.20 | -- | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 7* | -- | 225 | 0.40 | 2.62 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 224 | 2.38 | 4.61 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 168 | 1.16 | 4.13 | -- | ||
Hermes 4 70B (FP8) | 128k | Open | 7* | -- | 92 | 1.40 | 6.83 | -- | ||
Ministral 3 3B | 256k | Open | 7 | $0.13 | 410 | 0.96 | 2.18 | -- | ||
Ministral 3 3B | 131k | Open | 7 | $0.13 | 268 | 0.63 | 2.49 | -- | ||
Granite 4.1 8B | 131k | Open | 7* | -- | 108 | 0.77 | 5.41 | -- | ||
Sarvam 30B (high) | 64k | Open | 7* | -- | -- | -- | -- | -- | ||
Phi-4 Mini | 128k | Open | 6 | $0.00 | 43 | 0.84 | 12.36 | -- | ||
Jamba 1.7 Large | 256k | Open | 5* | -- | 59 | 1.46 | 9.98 | -- | ||
Granite 4.0 H Small | 128k | Open | 5* | -- | 346 | 10.26 | 11.71 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 5* | -- | 95 | 1.86 | 7.13 | -- | ||
Phi-4 | 16.4k | Open | 5* | -- | -- | -- | -- | -- | ||
Phi-4 | 16.4k | Open | 5* | -- | 74 | 0.87 | 7.64 | -- | ||
Nova Micro | 130k | Proprietary | 5* | -- | 300 | 0.89 | 2.55 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL | 128k | Open | 5* | -- | 197 | 1.15 | 3.69 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Open | 5* | -- | 94 | 4.48 | 9.81 | -- | ||
Phi-4 Multimodal | 128k | Open | 5* | -- | 18 | 0.82 | 29.24 | -- | ||
Reka Flash 3 | 54k | Open | 4* | -- | -- | -- | -- | -- | ||
Llama 3.2 11B (Vision) | 131k | Open | 3* | -- | 7 | 2.54 | 74.00 | -- | ||
Olmo 3 7B | 65.5k | Open | 3* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Open | 2* | -- | -- | -- | -- | -- | ||
LFM2.5-VL-1.6B | 32.8k | Open | 1* | -- | 395 | 1.86 | 3.12 | -- | ||
Tiny Aya Global | 8.19k | Open | 1* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Open | 1* | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (low) | 1M | Proprietary | -- | -- | 62 | 1.67 | 9.74 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | Proprietary | -- | -- | 68 | 30.48 | 37.86 | -- | ||
Claude Sonnet 5 (high) | 1M | Proprietary | -- | -- | 70 | 4.39 | 11.55 | -- | ||
Cogito v2.1 | 164k | Open | -- | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (medium) | 1M | Proprietary | -- | -- | 63 | 2.13 | 10.07 | -- | ||